A concept-based interpretable model for the diagnosis of choroid neoplasias using multimodal data

Diagnosing rare diseases remains a critical challenge in clinical practice, often requiring specialist expertise. Despite the promising potential of machine learning, the scarcity of data on rare diseases and the need for interpretable, reliable artificial intelligence (AI) models complicates development. This study introduces a multimodal concept-based interpretable model tailored to distinguish uveal melanoma (0.4-0.6 per million in Asians) from hemangioma and metastatic carcinoma following the clinical practice. We collected a comprehensive dataset on Asians to date on choroid neoplasm imaging with radiological reports, encompassing over 750 patients from 2013 to 2019. Our model integrates domain expert insights from radiological reports and differentiates between three types of choroidal tumors, achieving an F<sub>1</sub> score of 0.91. This performance not only matches senior ophthalmologists but also improves the diagnostic accuracy of less experienced clinicians by 42%. The results underscore the potential of interpretable AI to enhance rare disease diagnosis and pave the way for future advancements in medical AI.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-04-13
DOI
https://doi.org/10.1038/s41467-025-58801-7
Citations
10
Primary Topic
Retinal Imaging and Analysis
Type
article
Field-Weighted Citation Impact
13.60

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A concept-based interpretable model for the diagnosis of choroid neoplasias using multimodal data

Shi Gu, James C. Gee, Yifan Wu, Yueming Liu et al.
10 citations
Nature Communications
Retinal Imaging and Analysis
13.60
article

A concept-based interpretable model for the diagnosis of choroid neoplasias using multimodal data

Shi Gu, James C. Gee, Yifan Wu, Yueming Liu, Lihong Yang, Chunyan Lei, Michael S. Yao, Shiyi Yin, Wenbin Wei, Xuehui Shi, Yue Yang, Meixia Zhang, Dongjun Li, Wenli Yang, Yang Liu, Xuan Yang
article en
10 citations

Abstract

Diagnosing rare diseases remains a critical challenge in clinical practice, often requiring specialist expertise. Despite the promising potential of machine learning, the scarcity of data on rare diseases and the need for interpretable, reliable artificial intelligence (AI) models complicates development. This study introduces a multimodal concept-based interpretable model tailored to distinguish uveal melanoma (0.4-0.6 per million in Asians) from hemangioma and metastatic carcinoma following the clinical practice. We collected a comprehensive dataset on Asians to date on choroid neoplasm imaging with radiological reports, encompassing over 750 patients from 2013 to 2019. Our model integrates domain expert insights from radiological reports and differentiates between three types of choroidal tumors, achieving an F<sub>1</sub> score of 0.91. This performance not only matches senior ophthalmologists but also improves the diagnostic accuracy of less experienced clinicians by 42%. The results underscore the potential of interpretable AI to enhance rare disease diagnosis and pave the way for future advancements in medical AI.

Nature CommunicationsVol. 16(1)
Beijing Tongren Hospital (CN), University of Electronic Science and Technology of China (CN), Capital Medical University (CN), Sichuan University (CN), West China Hospital of Sichuan University (CN), Zhejiang Lab (CN), Zhejiang University of Technology (CN), University of Pennsylvania (US)
Key Programme
Openalex Percentile: Top 1%
Retinal Imaging and Analysis
13.60
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.